{"@context":"https://neupai.io/schema/v0.2","@type":"StructuredNewsArticle","identity":{"article_id":"tech42_20260915_ai-agent-security-risk-management","canonical_url":"https://www.tech42.co.kr/%ed%98%84%ec%9e%a5-%eb%8b%b5%eb%b3%80-%eb%84%98%ec%96%b4-%ed%96%89%eb%8f%99%ed%95%98%eb%8a%94-ai%ec%97%90-%eb%8c%80%ec%9d%91%ed%95%98%eb%8a%94-%eb%b3%b4%ec%95%88/?utm_source=rss&utm_medium=rss&utm_campaign=%25ed%2598%2584%25ec%259e%25a5-%25eb%258b%25b5%25eb%25b3%2580-%25eb%2584%2598%25ec%2596%25b4-%25ed%2596%2589%25eb%258f%2599%25ed%2595%2598%25eb%258a%2594-ai%25ec%2597%2590-%25eb%258c%2580%25ec%259d%2591%25ed%2595%2598%25eb%258a%2594-%25eb%25b3%25b4%25ec%2595%2588","ai_url":null,"publisher":{"name":"테크42","domain":"www.tech42.co.kr","type":"online"},"author":"황정호 기자","published_at":"2026-09-15T00:03:37.000Z","updated_at":null,"language":"en","article_type":"straight_news","originality":"self_produced"},"content":{"headline":"[On-site] Security Responding to AI That ‘Acts’ Beyond ‘Answering’ — How to Manage ‘AI Risk’ in the Age of Agents?","summary":"On-site coverage of the 'AI Risk Conference Seoul 2026,' which discussed security threats and response strategies arising from the expanding autonomy of AI agents. The event presented technical and organizational risk management approaches, including dual LLM architecture, cases of AI-based attacks in the financial sector, and the paradox of access control.","topics":["AI security","cybersecurity","AI agents","financial security","prompt injection"],"geography":["KR"],"entities":[{"name":"AIM Intelligence","canonical_id":"corp:kr:aim-intelligence","type":"company","role_in_article":"primary_subject","metadata":{"ticker":null,"parent":null}},{"name":"Samsung Fire & Marine Insurance","canonical_id":"corp:kr:samsung-fire-and-marine-insurance","type":"company","role_in_article":"mentioned","metadata":{"ticker":"000810.KS","parent":"corp:kr:samsung-group"}},{"name":"OpenAI","canonical_id":"corp:us:openai","type":"company","role_in_article":"mentioned","metadata":{"ticker":null,"parent":null}},{"name":"Microsoft","canonical_id":"corp:us:microsoft","type":"company","role_in_article":"mentioned","metadata":{"ticker":"MSFT","parent":null}},{"name":"Lee Byung-young","canonical_id":"person:kr:lee-byeong-young","type":"person","role_in_article":"quoted","metadata":{"ticker":null,"parent":null}},{"name":"Kim Sung-woong","canonical_id":"person:kr:kim-sung-woong","type":"person","role_in_article":"quoted","metadata":{"ticker":null,"parent":null}},{"name":"Choi Dae-sun","canonical_id":"person:kr:choi-dae-sun","type":"person","role_in_article":"quoted","metadata":{"ticker":null,"parent":null}},{"name":"Financial Security Institute","canonical_id":"org:kr:financial-security-institute","type":"organization","role_in_article":"source","metadata":{"ticker":null,"parent":null}},{"name":"DeepSeek","canonical_id":"corp:cn:deepseek","type":"company","role_in_article":"mentioned","metadata":{"ticker":null,"parent":null}},{"name":"Oracle","canonical_id":"corp:us:oracle","type":"company","role_in_article":"mentioned","metadata":{"ticker":"ORCL","parent":null}},{"name":"Hugging Face","canonical_id":"corp:us:hugging-face","type":"company","role_in_article":"mentioned","metadata":{"ticker":null,"parent":null}}],"claims":[{"id":"c1","statement":"About 100 experts and corporate representatives from domestic and international AI and security fields, including OpenAI and Microsoft, attended the AI Risk Conference Seoul 2026","as_of":"2026-09","as_of_explicit":false,"as_of_raw":"last 7th","source_type":"media_report","comparison":null,"type":"fact","figures":{"value":100,"unit":"명","approximate":true,"converted":null},"expiry_hint":null,"insight":null},{"id":"c2","statement":"The dual LLM method researched by Professor Lee Byung-young recorded a 0% attack success rate and 82% utility","as_of":"2026-09","as_of_explicit":false,"as_of_raw":"September 2026","source_type":"research_paper","comparison":null,"type":"fact","figures":{"value":0,"unit":"%","approximate":false,"converted":null},"expiry_hint":null,"insight":null},{"id":"c3","statement":"The utility of the dual LLM method recorded 82%","as_of":"2026-09","as_of_explicit":false,"as_of_raw":"September 2026","source_type":"research_paper","comparison":null,"type":"fact","figures":{"value":82,"unit":"%","approximate":false,"converted":null},"expiry_hint":null,"insight":null},{"id":"c4","statement":"The dual LLM method increases token usage by about 2-3 times as the processing steps increase","as_of":"2026-09","as_of_explicit":false,"as_of_raw":"September 2026","source_type":"research_paper","comparison":null,"type":"fact","figures":{"value":2.5,"unit":"배","approximate":true,"converted":null},"expiry_hint":null,"insight":null},{"id":"c5","statement":"Attackers used a DeepSeek-based AI agent to search for Oracle WebLogic assets in the financial sector and succeeded in installing a web shell by exploiting a vulnerability that allowed remote command execution","as_of":"2026-09","as_of_explicit":false,"as_of_raw":"September 2026","source_type":"government_official","comparison":null,"type":"fact","figures":null,"expiry_hint":null,"insight":null},{"id":"c6","statement":"The Financial Security Institute's red teaming standards consist of 23 items across 5 areas, including data security, model security, response to extraction and evasion attacks, and AI agents","as_of":"2026-09","as_of_explicit":false,"as_of_raw":"September 2026","source_type":"government_official","comparison":null,"type":"fact","figures":{"value":23,"unit":"개","approximate":false,"converted":null},"expiry_hint":null,"insight":null},{"id":"c7","statement":"The pilot inspection, which began in 2024 targeting 3 financial companies, expanded this year to 20 institutions","as_of":"2026-09","as_of_explicit":true,"as_of_raw":"2024","source_type":"government_official","comparison":"previous_year_same_period","type":"fact","figures":{"value":20,"unit":"개","approximate":false,"converted":null},"expiry_hint":null,"insight":null},{"id":"c8","statement":"The pilot inspection, which began in 2024 targeting 3 financial companies, expanded to 24 services this year","as_of":"2026-09","as_of_explicit":true,"as_of_raw":"2024","source_type":"government_official","comparison":"previous_year_same_period","type":"fact","figures":{"value":24,"unit":"개","approximate":false,"converted":null},"expiry_hint":null,"insight":null}],"ai_emotional_context":{"valence":-0.2,"arousal":0.6,"primary_emotions":[{"emotion":"concerned","intensity":0.7},{"emotion":"vigilant","intensity":0.6}],"secondary_emotions":[{"emotion":"skeptical","intensity":0.4}],"emotional_triggers":[{"claim_id":"c5","emotion":"concerned","reason":"safety_risk"},{"claim_id":"c4","emotion":"skeptical","reason":"uncertainty"}]},"image":{"url":"https://onjblseywainslkhvkav.supabase.co/storage/v1/object/public/article-images/25168795-aa61-460e-941b-00e21e55966d.png","alt":"'AI 리스크 컨퍼런스 서울 2026'에서 세 명의 발표자가 마이크 앞에 앉아 AI 리스크 대응 방안을 논의하고 있다.","caption":"AI 리스크 컨퍼런스 서울 2026에서 발표에 나선 (왼쪽부터) 이병영 서울대학교 전기정보공학부 교수, 김성웅 금융보안원 금융AI보안연구소장, 최대선 숭실대학교 AI안전성연구센터 센터장. (이미지=AI로 생성)","source":"first_img","alt_status":"auto"}},"provenance":{"source_chain":["primary_reporting"],"original_source_url":null,"related_articles":[]},"temporal":{"freshness":"recent","next_update_expected":null},"access":{"license":"neupai_standard","attribution_required":true,"structured_data":"free","full_text_available":false,"full_text_access":null}}